Senior Data Scientist (Time Series + ML) | 6+ Years

Cisco — Bangalore, India

Meet the Team The post-pandemic years have exposed inherent biases and limitations in human-driven and statistical/Traditional ML-based forecasting approaches. Cisco wasn’t immune and saw a sharp increase in backlogs, inventory levels, and supply chain costs. The Forecasting Data Science Team within Global Planning is solving this by pioneering the application of Causal AI to revolutionise Demand Forecasting and its Enterprise impact. We’re working to provide breakthrough levels of regime-resilient forecast accuracy, efficiency, and prescriptive insights that enable decision makers across Cisco and its Supply Chain to plan optimally. We are a bright, engaged, and friendly distributed team working with an industry-leading Causal AI ecosystem. Gartner has ranked Cisco’s Supply Chain to be #1 or #2 in the world over the last 5 years, and recognised this team in their Power of Profession 2024 Supply Chain awards as one of the top 5 in the Process and Technology Innovation category. Your Impact You will bring your skills, experience, and innovation to play a significant role in shaping our Causal AI-based forecasting system to improve decision making and drive operational performance and efficiency across Cisco’s Enterprise and Supply Chain functions. Responsibilities : - Develop, evolve, and sustain key elements of the Causal-AI based Forecasting system for Aggregated Demand. Analyse and sharpen the causal consideration of global financial markets, macro-economics, micro-economic and competitive factors in the Demand Forecasting models. Engineer model features from broad internal and external structured and unstructured datasets, discover and improve the natural segmentation for Demand based on these factors, resolve causality of the factors, and incorporate them into structural causal models. Develop high-quality, accurate models that are robust and have a long shelf life. Solve complicated research problems that push the boundaries of structural causal modelling and s

View on HireSetu